Search

Your search keyword '"Cho, Jinwoo"' showing total 435 results
Start Over Author "Cho, Jinwoo"
435 results on '"Cho, Jinwoo"'

44. Calibration‐free blood pressure estimation based on a convolutional neural network.

Author

Cho, Jinwoo, Shin, Hangsik, and Choi, Ahyoung

Subjects
*CONVOLUTIONAL neural networks, *DEEP learning, *STANDARD deviations, *INTENSIVE care patients, *WRIST watches, *BLOOD pressure, *DATA mining
Abstract

In this study, we conducted research on a deep learning‐based blood pressure (BP) estimation model suitable for wearable environments. To measure BP while wearing a wearable watch, it needs to be considered that computing power for signal processing is limited and the input signals are subject to noise interference. Therefore, we employed a convolutional neural network (CNN) as the BP estimation model and utilized time‐series electrocardiogram (ECG) and photoplethysmogram (PPG) signals, which are quantifiable in a wearable context. We generated periodic input signals and used differential and thresholding methods to decrease noise in the preprocessing step. We then applied a max‐pooling technique with filter sizes of 2 × 1 and 5 × 1 within a 3‐layer convolutional neural network to estimate BP. Our method was trained, validated, and tested using 2.4 million data samples from 49 patients in the intensive care unit. These samples, totaling 3.1 GB were obtained from the publicly accessible MIMIC database. As a result of a test with 480,000 data samples, the average root mean square error in BP estimation was 3.41, 5.80, and 2.78 mm Hg in the prediction of pulse pressure, systolic BP (SBP), and diastolic BP (DBP), respectively. The cumulative error percentage less than 5 mm Hg was 68% and 93% for SBP and DBP, respectively. In addition, the cumulative error percentage less than 15 mm Hg was 98% and 99% for SBP and DBP. Subsequently, we evaluated the impact of changes in input signal length (1 cycle vs. 30 s) and the introduction of noise on BP estimation results. The experimental results revealed that the length of the input signal did not significantly affect the performance of CNN‐based analysis. When estimating BP using noise‐added ECG signals, the mean absolute error (MAE) for SBP and DBP was 9.72 and 6.67 mm Hg, respectively. Meanwhile, when using noise‐added PPG signals, the MAE for SBP and DBP was 26.85 and 14.00 mm Hg, respectively. Therefore, this study confirmed that using ECG signals rather than PPG signals is advantageous for noise reduction in a wearable environment. Besides, short sampling frames without calibration can be effective as input signals. Furthermore, it demonstrated that using a model suitable for information extraction rather than a specialized deep learning model for sequential data can yield satisfactory results in BP estimation. We have developed a deep learning methodology to predict blood pressure, designed specifically for use in noisy wearable environments, and using input signals from electrocardiograms and photoplethysmograms. Through comprehensive experimentation, we determined which signals within electrocardiograms and photoplethysmograms are resilient to noise interference. Furthermore, we identified the optimal size, data type, and format of the input for an effective deep learning analysis. Based on these insights, we were able to construct a lightweight deep learning model that is well‐suited for these analytical tasks. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

49. Effects of Experimental Conditions on Extraction Yield of Extracellular Polymeric Substances by Cation Exchange Resin

Author

Cho, Jinwoo, Hermanowicz, Slawomir W, and Hur, Jin

Subjects
Cation Exchange Resins, Kinetics, Polymers, Sewage, General Science & Technology
Abstract

Effects of experimental conditions on the yield of extracellular polymeric substances (EPSs) extraction by cation exchange resin (CER) were investigated using activated sludge flocs. The experimental variables included resin dose, extraction time, sample dilution, and storage time. An empirical model was proposed to describe the kinetics of extraction process. The extraction yield increases with the extraction time and CER dose until it reached the maximum amount of EPS extraction. The maximum yield of EPS was affected as well by the sample dilution, exhibiting a decreasing trend with increasing dilution factor. It was also found that the amount of EPS extracted from a raw sample depends on the storage time. Once EPS was extracted from the sample, however, the EPS keeps its original quantity under storage at 4°C. Based on the model, the maximum amount of EPS extraction and yield rate could be estimated for different conditions. Comparing the model parameters allows one to quantitatively compare the extraction efficiencies under various extracting conditions. Based on the results, we recommend the original sample should be diluted with the volume ratio of above 1:2 and a raw sample should be treated quickly to prevent the reduction of sample homogeneity and original integrity.

Published
2012

Catalog

Books, media, physical & digital resources
See catalog results